NameSense Supported Formats — PDF, Images, Office and Text

What each format can provide
File type	Local information	Optional AI analysis	Keep in mind
Text-based PDF	File properties; existing title, author and page count	Extract details from text in selected pages	Metadata may be missing; verify extracted dates and authors
Scanned PDF	File properties; OCR depends on scan quality	Work from readable text and the AI model you configured	Check OCR, selected pages and legibility; some scans cannot be read
Photos and screenshots	Dimensions; capture date and other metadata when present	Describing the scene requires a compatible vision model	Screenshots often have no capture information; set a default value
Text and code	Name, dates, parent folder and other file properties	Extract titles and descriptions from readable text	Encoding, size and extraction limits still apply
Office, EPUB and EML	File properties and any readable content	Analyze the content that can be extracted	Not every attachment, embedded object or complex layout can be read

What each format can provide

File type

Local information

Optional AI analysis

Keep in mind

Text-based PDF

File properties; existing title, author and page count

Extract details from text in selected pages

Metadata may be missing; verify extracted dates and authors

Scanned PDF

File properties; OCR depends on scan quality

Work from readable text and the AI model you configured

Check OCR, selected pages and legibility; some scans cannot be read

Photos and screenshots

Dimensions; capture date and other metadata when present

Describing the scene requires a compatible vision model

Screenshots often have no capture information; set a default value

Text and code

Name, dates, parent folder and other file properties

Extract titles and descriptions from readable text

Encoding, size and extraction limits still apply

Office, EPUB and EML

File properties and any readable content

Analyze the content that can be extracted

Not every attachment, embedded object or complex layout can be read

PDFs and common images

PDF, JPG/JPEG, PNG, GIF, TIF/TIFF, WebP, HEIC/HEIF, BMP, AVIF, and SVG. The file must open normally.

Text, markup, and code

TXT, HTML/HTM, Markdown, LOG, JSON/JSONL/NDJSON, YAML, XML, CSV, TSV, and supported source files including Swift, JavaScript, TypeScript, Python, Go, and Rust.

Modern Office and OpenDocument

Word: DOCX, DOCM, DOTX, DOTM. Excel: XLSX, XLSM, XLTX, XLTM. PowerPoint: PPTX, PPTM, POTX, POTM. OpenDocument: ODT, ODS, ODP.

Rich text, ebooks, and email

RTF rich text, EPUB ebooks, and EML email. Being supported does not mean every attachment, embedded object, or complex layout can be fully read.

Scope and processing limits

Not supported: legacy .doc/.xls/.ppt, audio and video, and whole folders. Encrypted, damaged, oversized, or extraction-limited files may not be analyzable. If something fails, note the file type and error message, then contact support.

PDFs and common images

Text, markup, and code

Modern Office and OpenDocument

Rich text, ebooks, and email

Scope and processing limits

Next steps